KangchengLiu

CenterNet-CondInst

Instance Segmentation based on CenterNet and CondInst

AdversarialTexture

Adversarial Texture Optimization from RGB-D Scans (CVPR 2020).

VirtualScan

virtual scanner

3DMV

[ECCV'18] 3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation

spsg

sgnn

[CVPR'20] SG-NN: Sparse Generative Neural Networks for Self-Supervised Scene Completion of RGB-D Scans

ScanComplete

[CVPR'18] ScanComplete: Large-Scale Scene Completion and Semantic Segmentation for 3D Scans

Mono3D

Source code for "Mononizing Binocular Videos" (SIGGRAPH Asia 2020)

ssen

Code for Spatial Semantic Embedding Network:Fast 3D Instance Segmentation with Deep Metric Learning

Centerpoint_PC

DISN

DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstruction

DepthAwareCNN

Depth-aware CNN for RGB-D Segmentation, ECCV 2018

3DN

3DN: 3D Deformation Network, CVPR 2019

pytorch-psetae

PyTorch implementation of the model presented in "Satellite Image Time Series Classification with Pixel-Set Encoders and Temporal Self-Attention"

DOPE-ROS-D435

Object 6DoF Pose Estimation for Assembly Robots Trained on Synthetic Data - ROS Kinetic/Melodic Using Intel® RealSense D435

RGGNet

[RA-L 2020] Official Tensorflow Implementation for "RGGNet: Tolerance Aware LiDAR-Camera Online Calibration with Geometric Deep Learning and Generative Model", IEEE Robotics and Automation Letters 5.4 (2020): 6956-6963

R-PointHop

R-PointHop: A Green, Accurate and Unsupervised Point Cloud Registration Method

3DIoUMatch

[CVPR 2021] PyTorch implementation of 3DIoUMatch: Leveraging IoU Prediction for Semi-Supervised 3D Object Detection.

DMRDenoise

:snowman: Differentiable Manifold Reconstruction for Point Cloud Denoising (ACM MM 2020)

YOGO

Official implementation of YOGO for point-cloud processing

NDT-Transformer

This github is a supplementary material including data, code, trained model and demo for the paper "NDT-Transformer: Large-Scale 3D Point Cloud Localisation using the Normal Distribution Transform Representation".

PointCloudRegistrationTool

Automatically registers (aligns) and visualizes point clouds, or processes a whole bunch at once

DeepGlobalRegistration

[CVPR 2020 Oral] A differentiable framework for 3D registration

ColorConsistency

Improving color consistency across multiple images via global optimization on the color remapping curves. [ICCVW 2017 & ISPRS Journal 2019]

PAM

Repository for "Parallax Attention for Unsupervised Stereo Correspondence Learning", TPAMI 2020

CrazySLAM

SLAM algorithm with ultrasound range input implemented on a Crazyflie drone

PanopticFCN

Fully Convolutional Networks for Panoptic Segmentation (CVPR2021 Oral)

point-transformer-pytorch

Implementation of the Point Transformer layer, in Pytorch

HighDimConvNets

[CVPR 2020 Oral] High-dimensional Convolutional Networks for Geometric Pattern Recognition

FLOT

FLOT: Scene Flow Estimation by Learned Optimal Transport on Point Clouds